© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44398
    Prev
    Next
    INDEX
    Explanations

    Tank meta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Universit
    0.47
    ண்ட
    0.45
    treatment
    0.44
     hvil
    0.42
    throp
    0.42
     behand
    0.41
     \}
    0.41
    tem
    0.41
     Treatment
    0.41
     Behandlung
    0.40
    POSITIVE LOGITS
    ሖ
    0.52
     timezone
    0.50
    ה
    0.49
    лесо
    0.48
     overdraft
    0.48
     vacancies
    0.47
     heartwarming
    0.46
     caravans
    0.46
     toNumber
    0.45
     новое
    0.44
    Activations Density 0.000%

    No Known Activations